prikaz prve stranice dokumenta Detekcija potresa korištenjem vremensko-frekvencijskih predstava seizmograma
Access restricted to students and staff of home institution
master's thesis
Detekcija potresa korištenjem vremensko-frekvencijskih predstava seizmograma
2020. urn:nbn:hr:190:660045
Njirjak, Marko
University of Rijeka
Faculty of Engineering
Department of Computer Engineering
Section of Intelligent Computing Systems

Cite this document

Njirjak, M. (2020). Detekcija potresa korištenjem vremensko-frekvencijskih predstava seizmograma (Master's thesis). Rijeka: University of Rijeka, Faculty of Engineering. Retrieved from https://urn.nsk.hr/urn:nbn:hr:190:660045

Njirjak, Marko. "Detekcija potresa korištenjem vremensko-frekvencijskih predstava seizmograma." Master's thesis, University of Rijeka, Faculty of Engineering, 2020. https://urn.nsk.hr/urn:nbn:hr:190:660045

Njirjak, Marko. "Detekcija potresa korištenjem vremensko-frekvencijskih predstava seizmograma." Master's thesis, University of Rijeka, Faculty of Engineering, 2020. https://urn.nsk.hr/urn:nbn:hr:190:660045

Njirjak, M. (2020). 'Detekcija potresa korištenjem vremensko-frekvencijskih predstava seizmograma', Master's thesis, University of Rijeka, Faculty of Engineering, accessed 09 November 2024, https://urn.nsk.hr/urn:nbn:hr:190:660045

Njirjak M. Detekcija potresa korištenjem vremensko-frekvencijskih predstava seizmograma [Master's thesis]. Rijeka: University of Rijeka, Faculty of Engineering; 2020 [cited 2024 November 09] Available at: https://urn.nsk.hr/urn:nbn:hr:190:660045

M. Njirjak, "Detekcija potresa korištenjem vremensko-frekvencijskih predstava seizmograma", Master's thesis, University of Rijeka, Faculty of Engineering, Rijeka, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:190:660045

Please login to the repository to save this object to your list.
Metadata
TitleDetekcija potresa korištenjem vremensko-frekvencijskih predstava seizmograma
Title (english)Earthquake detection Using Seismogram Time-Frequency Representations
AuthorMarko Njirjak
MentorIvan Štajduhar (mentor)
MentorJonatan Lerga (komentor)
Committee memberGoran Mauša (predsjednik povjerenstva)
Committee memberSandi Ljubić (član povjerenstva)
Committee memberIvan Štajduhar (član povjerenstva)
GranterUniversity of Rijeka
Faculty of Engineering
(Department of Computer Engineering)
(Section of Intelligent Computing Systems)
Rijeka
Defense date and country2020-07-14, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Ovaj rad se pozabavio idejom da različite vremensko-frekvencijske predstave seizmogramskih podataka mogu imati značajan utjecaj na točnost detekcije potresa korištenjem konvolucijskih neuronskih mreža. Korišteno je devet vremensko-frekvencijskih transformacija, te tri afirmirane konvolucijske neuronske mreže. Rezultati pokazuju da kombinacija pseudo Wigner-Ville vremensko-frekvencijske distribucije i AlexNet arhitekture poboljšava rezultate baznog modela za 1,56 postotnih bodova. Navedeno može imati značajan odjek u području seizmologije s obzirom na činjenicu da se točnije klasificiraju podaci koji su do tada bili skriveni u seizmološkom šumu.
Abstract (english)
This paper addressed the idea that different time-frequency representations of seismogram data can have a significant impact on the accuracy of earthquake detection using convolutional neural networks. Nine time-frequency transformations and three well-established convolutional neural networks were used. The results show that the combination of the pseudo Wigner-Ville timefrequency distribution and the AlexNet architecture improves the results of the base model by 1.56 percentage points. This can have a significant impact in the field of seismology due to the fact that the data that were previously hidden in the seismological noise are now classified more accurately.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:190:660045
Study programmeTitle: Computer Engineering
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2020-12-16 12:08:30